SeaShell Intake takes a call transcript and extracts the structured intent inside it: commitments, decisions, facts, people, and scope changes, each tagged with who said it and the line it came from. It then files each item where you keep that kind of note and remembers the choice, so it files the same way next time. The engine ships in SeaShell today behind the paid tier, and SeaShell Pro is not yet on sale.
From transcript to filed knowledge
A consultant's commitments and decisions live inside 1-hour call recordings and then rot, because turning them into filed notes is manual work.
Intake runs a single extraction pass over each transcript and pulls out the items that matter, each tagged with who said it and a link back to the line it came from. What was buried in an hour-long recording becomes a short list of commitments, decisions, and facts you can act on.
It learns your filing system
The first time Intake sees a kind of item for a client, it asks once where you want it filed, then remembers.
Commitments for one client might go to a checklist, decisions to a decision log, people to your knowledge base. Intake learns these routing rules per client and per item type, files new items automatically, and lets you correct any choice, which updates the rule. The agent learns your information architecture instead of being told it every time.
Drop a file in; a Fireflies pull is still to come
Intake works with any notetaker today through 1 path: dropping an exported transcript into the project.
The file-drop source is built and is what runs now. A Fireflies integration that pulls finished calls in automatically is designed but not yet implemented. The same extraction and filing applies either way, and the capability is opt-in per workspace.
Availability
Intake is 1 of the 8 record engines in SeaShell, and it sits behind the paid tier rather than the free core.
The engine is built and running in the product. It is gated to SeaShell Pro, and Pro does not have a checkout yet, so it is not something you can buy today. Shipped, the automated work log, is the one record engine available free right now.
Frequently asked questions
- Is SeaShell transcript extraction available now?
- The engine is built and running in SeaShell, but it sits behind the paid tier and SeaShell Pro is not yet on sale, so you cannot purchase access today.
- Which notetakers does it support?
- Any notetaker, by dropping an exported transcript file into the project. An automatic Fireflies pull is designed but not yet built.
- What does it extract?
- Commitments, decisions, facts, people, scope changes, and action items, each linked back to the transcript line it came from.
- Do I have to tell it where to file everything?
- Only once per kind of item per client. After that it files the same way automatically, and you can change any rule later by correcting a filing.
- Which record engine can I use for free?
- Shipped, the automated work log. It reads your commits and sessions and is on by default in the free core.
Try SeaShell in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install SeaShellRelated guides
Atlas with Claude Fable 5 in 2026
In 2026, Atlas developers can leverage Claude Fable 5 for complex coding tasks. Its 1M token context and high capability make it ideal for precise planning, despite its premium $10/$50 per Mtok cost.
Atlas with Phi-4 (local via Ollama) in 2026
Explore Atlas with Phi-4 (local via Ollama) in 2026. This 14B parameter model offers strong reasoning for Atlas's planning agent, is free (self-hosted), and fits on a 12GB GPU, though its 16K token context window limits
Atlas with MiniMax-M2.7-highspeed in 2026
Drive Atlas with MiniMax-M2.7-highspeed in 2026 for rapid, interactive coding. Get 200K context and priority serving at $0.60/$2.40, ideal for human-in-the-loop agentic workflows.
Add a Regression Test for a Bug Fix with Atlas in 2026
How to add a regression test with Atlas in 2026: red first, then green. bash records the exit code, write creates the failing test, and edit applies the fix.
Atlas with Qwen2.5 72B (local via Ollama) in 2026
Explore Atlas with Qwen2.5 72B (local via Ollama) for fully air-gapped, free AI coding. Leverage its 32,768 token context window for secure, self-hosted development in 2026.
Atlas with Kimi K2 Thinking (2026)
Atlas with Kimi K2 Thinking (2026): Powerful reasoning for complex code issues at $0.60 per Mtok input, featuring a 262K token context window. Ideal for deep diagnostics.
Atlas with Qwen Plus in 2026
For Atlas developers in 2026, Qwen Plus from Alibaba offers a powerful 1,000,000 token context window at an exceptional $0.40 per Mtok input price, ideal for complex coding tasks and deep code analysis.
Atlas with Llama 3.1 70B (local via Ollama) in 2026
In 2026, drive Atlas with Llama 3.1 70B (local via Ollama) for powerful, private AI coding. Leverage its 128,000 token context window and 70B quality for complex tasks, all self-hosted and free.